kp7742/YALM-130M

README.md

@@ -0,0 +1,48 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: YALM_130M
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# YALM_130M
+
+This model was trained from scratch on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.006
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: warmup_stable_decay
+- lr_scheduler_warmup_steps: 4000
+- training_steps: 40000
+
+### Framework versions
+
+- Transformers 4.56.2
+- Pytorch 2.7.1+cu128
+- Datasets 4.1.1
+- Tokenizers 0.22.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.9943848331453324,
+    "eval_loss": 2.4558820724487305,
+    "eval_runtime": 21.5064,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 464.978,
+    "eval_steps_per_second": 7.3,
+    "perplexity": 11.656711079135674,
+    "total_flos": 2.850359340957696e+19,
+    "train_loss": 2.7858428371429445,
+    "train_runtime": 155503.5731,
+    "train_samples": 20595656,
+    "train_samples_per_second": 131.701,
+    "train_steps_per_second": 0.257
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.022,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    1
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.56.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a2548390395fa33a176db64b132dc807585b9da9f953bc6b1b66a0705dcac5
+size 260096992

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|eot|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|eot|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eot|>",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403f6f87a8bcccdb8514a6f1482fc5b9c2c345bfc343967c6565ad54ead4be34
+size 5841